KR102621569B1 - Method, system, and non-transitory computer-readable recording medium for controlling a robot - Google Patents

Abstract

According to one aspect of the present invention, a method for controlling a robot includes determining a first comparison target axis with reference to a first target area specified by a camera module of the robot, and determining a first comparison target axis, which is specified by a scanner module of the robot and 1 determining a second comparison target axis with reference to a second target area associated with the target area, and a reference coordinate system associated with the camera module with reference to the relationship between the first comparison target axis and the second comparison target axis. A method including the step of correcting is provided.

Description

Method, system and non-transitory computer-readable recording medium for controlling a robot {METHOD, SYSTEM, AND NON-TRANSITORY COMPUTER-READABLE RECORDING MEDIUM FOR CONTROLLING A ROBOT}

The present invention relates to a method, system, and non-transitory computer-readable recording medium for controlling a robot.

Because robots can automate difficult tasks or repetitive operations, they are used to replace or assist humans in various fields. In recent years, various studies have been conducted on technologies for correcting errors or errors that occur in the process of operating a robot.

An example of the prior art in this regard is the technology disclosed in Korean Patent Publication No. 10-0914211, which provides two-dimensional correction for a correction index having a plurality of square grid patterns photographed through a camera. Receive an index image, extract a plurality of feature data including vertex coordinate information and vertex connection information between the grid patterns from the corrected index image, and configure a distortion correction algorithm using the coordinate information of the plurality of feature data. A distortion image correction method has been introduced that includes calculating a distortion correction coefficient and generating a correction file using the calculated coefficient.

However, the technologies introduced so far, including the above-mentioned conventional technologies, are mainly interested in ways to improve the quality of image information or sensing information acquired by robots, and involve hardware modules (hardware modules) that acquire image information or sensing information. For example, there is interest in ways to improve errors that occur in the process of assembling or installing camera modules, scanner modules, etc., and errors that occur in such hardware modules due to environmental factors (e.g., temperature). There wasn't.

In general, a robot has various hardware modules based on a three-dimensional coordinate system, and the modules are interconnected. For example, a camera module is located in a position (or direction) other than the designated location (or direction). or direction), problems related to matching or linking between the coordinate system of the camera module and the coordinate system of other hardware modules, for example, the scanner module, may occur, which can be a major cause of malfunction of the robot. Additionally, in the case of robots operated outdoors, when the temperature of the camera module (for example, a 3D camera module) installed on the robot increases due to sunlight, etc., a recognition error related to the roll direction occurs (specifically, There was a problem that as the temperature increased, the angle difference with the ground surface based on the roll direction increased. Additionally, there may be cases where the robot cannot move the desired distance or rotate at the desired angle due to conditions related to the movement module installed on the robot (e.g., wheel wear, change in wheel base length, floor condition, etc.). did.

Accordingly, the present inventor(s) propose a new and advanced technology that can precisely correct errors associated with the robot's hardware modules, specifically camera modules or movement modules.

The purpose of the present invention is to solve all the problems of the prior art described above.

In addition, the present invention relates to a relationship between a comparison target axis determined by a camera module (e.g., a 3D camera) and a comparison target axis determined by a scanner module (e.g., a LIDAR sensor). The purpose is to correct errors according to the installation location or installation direction of the camera module by referencing and correcting the reference coordinate system associated with the camera module.

In addition, the present invention corrects the reference coordinate system associated with the camera module by referring to the relationship between the floor surface on which the robot is located and the reference surface specified by the camera module, thereby correcting errors (specifically, the roll direction in the roll direction) that occur due to an increase in temperature. The purpose is to correct errors.

In addition, the present invention corrects the movement attribute information of the robot (for example, the size of the wheel, the length of the wheel base, etc.) of the robot based on a predetermined point specified by the robot's scanner module, so that the actual moving distance of the robot and the robot The difference between the recorded distance traveled (e.g., the distance measured by the robot's odometer) or the robot's actual rotation angle and the robot's recorded rotation angle (e.g., the distance measured by the robot's odometer). Another purpose is to correct the difference between the measured rotation angles.

A representative configuration of the present invention to achieve the above object is as follows.

According to one aspect of the present invention, a method for controlling a robot includes determining a first comparison target axis with reference to a first target area specified by a camera module of the robot, and determining a first comparison target axis, which is specified by a scanner module of the robot and 1 determining a second comparison target axis with reference to a second target area associated with the target area, and a reference coordinate system associated with the camera module with reference to the relationship between the first comparison target axis and the second comparison target axis. A method including the step of correcting is provided.

According to another aspect of the present invention, a system for controlling a robot, wherein a first comparison target axis is determined with reference to a first target area specified by a camera module of the robot, and the first axis is specified by a scanner module of the robot. 1. A comparison axis determination unit that determines a second comparison axis with reference to a second target area associated with the target area, and the camera module with reference to the relationship between the first comparison axis and the second comparison axis. A system including a correction unit that corrects an associated reference coordinate system is provided.

In addition, another method for implementing the present invention, another system, and a non-transitory computer-readable recording medium recording a computer program for executing the method are further provided.

According to the present invention, reference is made to the relationship between the comparison axis determined by a camera module (e.g., a 3D camera) and the comparison axis determined by a scanner module (e.g., a LIDAR sensor). By correcting the reference coordinate system associated with the camera module, errors depending on the installation location or direction of the camera module can be corrected.

In addition, according to the present invention, by correcting the reference coordinate system associated with the camera module with reference to the relationship between the floor surface on which the robot is located and the reference surface specified by the camera module, errors occurring due to temperature increase (specifically, roll direction error) can be corrected.

In addition, according to the present invention, the robot's movement attribute information (for example, wheel size, wheel base length, etc.) is corrected based on a predetermined point specified by the robot's scanner module, and the robot's actual movement distance and The difference between the robot's recorded distance traveled (e.g., the distance measured by the robot's odometer) or the robot's actual rotation angle and the robot's recorded rotation angle (e.g., the distance measured by the robot's odometer). The difference between the rotation angles) can be corrected.

1 is a diagram schematically showing the configuration of an entire system for controlling a robot according to an embodiment of the present invention.
Figure 2 is a diagram illustrating the internal configuration of a correction system according to an embodiment of the present invention.
3 to 6 are diagrams illustrating a process for correcting a reference coordinate system associated with a camera module of a robot according to an embodiment of the present invention.
Figure 7 is a diagram illustrating a process for correcting movement attribute information of a robot according to an embodiment of the present invention.
8 and 9 are diagrams illustrating the structure of a robot according to an embodiment of the present invention.

The detailed description of the present invention described below refers to the accompanying drawings, which show by way of example specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different from one another but are not necessarily mutually exclusive. For example, specific shapes, structures and characteristics described herein may be implemented with changes from one embodiment to another without departing from the spirit and scope of the invention. Additionally, it should be understood that the location or arrangement of individual components within each embodiment may be changed without departing from the spirit and scope of the present invention. Accordingly, the detailed description described below is not to be taken in a limiting sense, and the scope of the present invention should be taken to encompass the scope claimed by the claims and all equivalents thereof. Like reference numbers in the drawings indicate identical or similar elements throughout various aspects.

Hereinafter, several preferred embodiments of the present invention will be described in detail with reference to the attached drawings in order to enable those skilled in the art to easily practice the present invention.

Configuration of the entire system

1 is a diagram schematically showing the configuration of an entire system for controlling a robot according to an embodiment of the present invention.

As shown in FIG. 1, the entire system according to an embodiment of the present invention may include a communication network 100, a correction system 200, and a robot 300.

First, according to an embodiment of the present invention, the communication network 100 can be configured regardless of communication mode, such as wired communication or wireless communication, and may include a local area network (LAN), a metropolitan area network (MAN), or a local area network (LAN). It can be composed of various communication networks such as (Network) and Wide Area Network (WAN). Preferably, the communication network 100 referred to in this specification may be the known Internet or World Wide Web (WWW). However, the communication network 100 is not necessarily limited thereto and may include at least a portion of a known wired or wireless data communication network, a known telephone network, or a known wired or wireless television communication network.

For example, the communication network 100 is a wireless data communication network, including Wi-Fi communication, WiFi-Direct communication, Long Term Evolution (LTE) communication, and Bluetooth communication (more specifically, low-power Bluetooth). (BLE; Bluetooth Low Energy) communication), infrared communication, ultrasonic communication, etc. may be implemented at least in part.

Next, the correction system 200 according to an embodiment of the present invention can communicate with the robot 300, which will be described later, through the communication network 100, and the camera module of the robot 300 (e.g., 3 A first comparison target axis is determined with reference to a first target area specified by a dimensional camera, and a first comparison target axis is specified by a scanner module (e.g., LiDAR sensor) of the robot 300 and is associated with the first target area. 2 Determines the second comparison target axis with reference to the target area, and performs the function of correcting the reference coordinate system associated with the camera module of the robot 300 by referring to the relationship between the first comparison target axis and the second comparison target axis. You can.

Meanwhile, although the correction system 200 has been described as above, this description is illustrative, and at least some of the functions or components required for the correction system 200 may be used as a robot 300 or an external system ( It is obvious to those skilled in the art that it may be implemented within the robot 300 (not shown) or included within the robot 300 or an external system. Additionally, in some cases, all functions and all components of the correction system 200 may be fully realized within the robot 300 or may be entirely included within the robot 300.

Next, the robot 300 according to an embodiment of the present invention can communicate with the correction system 200 through the communication network 100, and performs a predetermined function or assigned task (e.g., A device capable of autonomously performing food serving, container retrieval, etc.), modules (e.g. grabs, robotic arm modules, etc.) for loading and unloading objects (e.g. food trays), and surrounding environment information. It may include at least one module selected from the group consisting of a camera module or scanner module for acquiring a camera module or a scanner module, a display and speaker module for providing various images or voices, and a drive module (for example, a motor, etc.) for moving the robot 300. You can. For example, the robot 300 may be a robot that has characteristics or functions similar to at least one of a guide robot, a transport robot, a cleaning robot, a medical robot, an entertainment robot, a pet robot, and an unmanned flying robot.

Meanwhile, according to one embodiment of the present invention, the robot 300 may include an application that supports functions according to the present invention, such as correcting a reference coordinate system associated with a camera module. Such an application may be downloaded from the correction system 200 or an external application distribution server (not shown).

Configuration of the compensation system

Below, we will look at the internal structure of the correction system 200 and the function of each component, which performs important functions for implementing the present invention.

Figure 2 is a diagram illustrating the internal configuration of the correction system 200 according to an embodiment of the present invention.

Referring to FIG. 2, the correction system 200 according to an embodiment of the present invention may include a comparison axis determination unit 210, a correction unit 220, a communication unit 230, and a control unit 240. According to an embodiment of the present invention, the comparison target axis determination unit 210, correction unit 220, communication unit 230, and control unit 240 are programs, at least some of which communicate with an external system (not shown). These can be modules. These program modules may be included in the correction system 200 in the form of operating systems, application modules, and other program modules, and may be physically stored in various known storage devices. Additionally, these program modules may be stored in a remote memory device capable of communicating with the calibration system 200. Meanwhile, these program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types according to the present invention.

First, the comparison axis determination unit 210 according to an embodiment of the present invention may perform the function of determining the first comparison axis with reference to the first target area specified by the camera module of the robot 300. . For example, the first target area according to an embodiment of the present invention may be a point where two or more edges meet or an area containing an object in the place (or space) where the robot 300 is located. More specifically, the first target area may include a wall corner area (more specifically, a vertex area of the wall corner) where the robot 300 is located.

For example, referring to (a) and (b) of FIGS. 3, the first target area is the vertex 310 of the wall corner of the place where the robot 300 is located (e.g., a room in the shape of a rectangular parallelepiped). It may be an area (for example, such an area may be specified in the form of a point cloud, polygon, etc. by a camera module), and the comparison target axis determination unit 210 may be located at the corresponding vertex 310 of the first target area. ) The first comparison target axis 315 can be determined by referring to the three edges specified around ). More specifically, the comparison target axis determination unit 210 specifies a plurality of axes based on each of three corners forming 90 degrees with respect to the above vertex, and sets the plurality of axes as the first comparison target axis 315. You can decide.

For another example, the first target area is an area containing the vertices of a rectangular parallelepiped-shaped bed in a place where the robot 300 is located (e.g., a bedroom) (e.g., this area is a point cloud using a camera module. , may be specified in the form of a polygon, etc.), and the comparison axis determination unit 210 may determine the first comparison axis by referring to three edges specified around the corresponding vertex of the first target area. . More specifically, the comparison target axis determination unit 210 may specify a plurality of axes based on each of three corners forming 90 degrees with respect to the above vertex, and determine the plurality of axes as the first comparison target axis. .

Additionally, the comparison axis determination unit 210 may perform a function of determining a second comparison axis with reference to a second target area that is specified by the scanner module of the robot 300 and is associated with the first target area. For example, the second target area according to an embodiment of the present invention may be a point where two or more edges meet or an area containing an object in the place (or space) where the robot 300 is located, and the first target area It may be the same as or have a predetermined positional relationship or preset relationship with it. More specifically, the second target area is an area that includes another vertex that shares one or more edges among the three edges specified based on the vertex included in the first target area, or is an area that includes a vertex included in the first target area and a predetermined number of edges. It may be an area that includes other vertices in a positional relationship (e.g., symmetrical movement, parallel movement, rotational movement, etc.). For example, when the place where the robot 300 is located is a room in the shape of a rectangular parallelepiped, if the first target area is an area that includes a specific vertex of a wall corner of the room, the second target area is an area that includes the remaining vertices excluding the specific vertex. It may be an area containing any one of the following.

For example, referring again to (a) and (b) of FIG. 3, the area including the lower vertex 310 of the corner of the wall of the place where the robot 300 is located (e.g., a room in the shape of a rectangular parallelepiped) In the case of the first target area discussed above, the second target area associated with the first target area is an area containing the upper vertex of the corresponding wall corner (e.g., such area is a point cloud, polygon, etc. may be specified in the form of), and the comparison axis determination unit 210 may determine the second comparison axis 325 by referring to three corners specified based on the upper vertex. More specifically, the comparison target axis determination unit 210 specifies a plurality of axes based on each of three corners forming 90 degrees with respect to the upper vertex, and refers to the plurality of axes as the second comparison target axis 325. can be decided.

Next, the correction unit 220 according to an embodiment of the present invention associates the camera module with reference to the relationship between the first comparison axis and the second comparison axis determined by the comparison axis determination unit 210. The reference coordinate system can be corrected. The reference coordinate system associated with the camera module according to an embodiment of the present invention is a predetermined coordinate system (e.g., rectangular coordinate system, cylindrical coordinate system, spherical coordinate system, etc.) used by the camera module to recognize real-world objects or the optical axis of the camera module. It may include a coordinate system specified based on . Meanwhile, this reference coordinate system may be determined with reference to the position or direction in which the camera module is installed or fixed to the robot 300.

For example, the correction unit 220 translates or rotates the reference coordinate system before correction of the camera module by referring to the distance or angle (or angle between the two) specified by comparing the first comparison target axis and the second comparison target axis. By doing so, the calibrated reference coordinate system of the camera module can be determined.

More specifically, referring to FIG. 4, the correction unit 220 uses a base reference coordinate system 401 (e.g., a robot operating system; (or a reference coordinate system associated with the scanner module) and a pre-calibration reference coordinate system 402 of the camera module (e.g., a coordinate system specified based on the base_footprint defined in the ROS platform) (e.g., a reference coordinate system specified based on the camera_fixed_link defined in the ROS platform) The relationship 407 between the coordinate systems) can be determined. For example, this relationship may be determined by referring to a preset or predetermined positional relationship (for example, a positional relationship between the center of the floor where the robot 300 is located and the point where the camera module is installed). Next, the correction unit 220 specifies the first comparison target axis 403 based on the base reference coordinate system 401 (or a reference coordinate system associated with the scanner module), and the reference coordinate system 402 before correction of the camera module. ), the second comparison target axis 404 can be specified based on. Next, the correction unit 220 determines the relationship 407 between the base reference coordinate system 401 and the pre-correction reference coordinate system 402 of the camera module, the first comparison target axis 403, and the second comparison target axis ( By correcting the reference coordinate system 402 before correction of the camera module with reference to the relationship 405 between 404) (408), the corrected reference coordinate system 406 of the camera module can be determined. Meanwhile, in the above correction process, correction may be performed by considering the extrinsic parameters and intrinsic parameters of the camera module (409, 410).

Referring to (a) of FIG. 5, when the wall corner 501 is specified through the camera module and the scanner module (for example, a point cloud for the wall corner is acquired by each of the camera module and the scanner module) , Before correction, there may be a difference between the position 510 of the wall corner specified in the base reference coordinate system (or the reference coordinate system of the scanner module) and the position 520 of the wall corner specified in the reference coordinate system 402 of the camera module. However, referring to (b) of FIG. 5, after correction, the position of the wall corner specified in the base reference coordinate system (or the reference coordinate system of the scanner module) 510 and the wall corner specified in the reference coordinate system 402 of the camera module The positions 520 may coincide with each other.

Additionally, the correction unit 220 may correct the reference coordinate system associated with the camera module by referring to the relationship between the floor surface on which the robot 300 is located and the reference surface specified by the camera module.

For example, the correction unit 220 may correct the reference coordinate system associated with the camera module by referring to the angle between the floor surface where the robot 300 is located and the reference plane specified by the camera module. For example, referring to FIG. 6, the correction unit 220 may determine the angle and rotation axis of the floor surface 610 on which the robot 300 is located and the reference surface 620 specified by the camera module (e.g. , when the normal vector of the floor surface 610 is N1 and the normal vector of the reference surface 620 is N2, the above rotation axis is calculated based on the outer product of N1 and N2, and the arccosine of the inner product of N1 and N2 ( The above included angle can be calculated based on the arccos calculation), and the reference coordinate system associated with the camera module is corrected based on the result of applying Rodrigues' rotation formula based on the above included angle and rotation axis. can do.

For another example, the correction unit 220 may specify a candidate reference surface using at least three points on the ground surface specified by the camera module. Next, the correction unit 220 may determine the number of points that exist within a predetermined distance from the candidate reference surface among the plurality of points on the ground surface specified by the camera module. Next, the correction unit 220 selects a candidate reference surface whose number of points is above a predetermined level or more (for example, a candidate reference surface with the largest number of points existing within a predetermined distance) among a plurality of candidate reference surfaces including the above candidate reference surface. can be determined as a reference plane specified by the camera module.

For another example, the correction unit 220 may specify a candidate reference surface using at least three points on the ground surface specified by the camera module. Next, the correction unit 220 may determine a point that exists within a predetermined distance from the candidate reference surface among a plurality of points on the ground surface specified by the camera module. Next, the correction unit 220 performs regression analysis (e.g., logistic regression analysis, etc.) on the above point with reference to the above point among the plurality of candidate reference surfaces including the above candidate reference surface. (Referring to the results), the reference plane specified by the camera module can be determined.

In addition, the correction unit 220 may correct the movement attribute information of the robot 300 with reference to at least one of the movement distance and rotation angle of the robot 300 determined based on a predetermined point specified by the scanner module. . The movement attribute information of the robot 300 according to an embodiment of the present invention includes information about the size of the wheel (or wheels) of the robot 300 (e.g., radius, circumference length, etc.), the length of the wheel base, etc. You can.

For example, referring to FIG. 7, the correction unit 220 moves the robot 300 forward or backward 710 (710) based on a predetermined point 701 (for example, a wall corner) specified by the scanner module. Alternatively, it can be moved forward or backward repeatedly, and the actual moving distance of the robot 300 specified based on the predetermined point 701 above (for example, the robot 300 based on the predetermined point 701 above) The actual moving distance can be calculated by calculating the position of) and the recorded moving distance of the robot 300 (e.g., the distance measured by the odometer of the robot 300). (Meanwhile, this operation may be performed repeatedly), and information about the size of the wheels of the robot 300 can be corrected based on the difference. For example, assuming that the actual radius of the wheel and the estimated radius of the wheel are r' and r, respectively, and that the angular velocities of the left and right wheels are W _L and W _R , respectively, the estimated translation speed of the wheel (v_estimated) and the actual translation speed of the wheel are The difference between (v_real), that is, (v_real-v_estimated)/v_real, can be calculated as 1-r/r', and the actual radius of the wheel can be specified as r'=r/(1-difference).

For another example, the correction unit 220 may rotate (or repeatedly rotate) the robot 300 clockwise or counterclockwise 720 based on a predetermined point specified by the scanner module. The actual rotation angle of the robot 300 specified based on a predetermined point (for example, the actual rotation angle can be calculated by calculating the angle of the robot 300 based on the predetermined point above) and the robot 300 Calculate the difference between the recorded rotation angles (e.g., the rotation angle measured by the odometer of the robot 300) and correct information regarding the length of the wheel base of the robot 300 based on the difference. You can. For example, assuming that the actual length of the wheel base and the estimated length of the wheel base are l' and l, respectively, and that the angular velocities of the left and right wheels are W _L and W _R , respectively, the estimated rotational speed of the wheel (w_estimated) and the actual length of the wheel The difference between rotational speeds (w_real), i.e. (w_real-w_estimated)/w_real, can be calculated as 1-l'/l, and the actual length of the wheel base can be specified as l'=l*(1-difference) .

Next, according to an embodiment of the present invention, the communication unit 230 may perform a function that enables data transmission and reception to/from the comparison target axis determination unit 210 and the correction unit 220.

Finally, according to an embodiment of the present invention, the control unit 240 may perform a function of controlling the flow of data between the comparison axis determination unit 210, the correction unit 220, and the communication unit 230. That is, the control unit 240 according to an embodiment of the present invention controls the data flow to/from the outside of the compensation system 200 or the data flow between each component of the compensation system 200, thereby controlling the comparison target axis determination unit. 210, the correction unit 220, and the communication unit 230 can each be controlled to perform their own functions.

Example

It can be assumed that the robot 300 according to an embodiment of the present invention is located in a restaurant.

First, according to one embodiment of the present invention, the robot 300 can be moved to a corner of a wall in a restaurant. Such a restaurant may be a rectangular parallelepiped-shaped place.

Then, according to one embodiment of the present invention, the first comparison target axis is determined with reference to the wall corner area specified by the camera module of the robot 300, and the first comparison target axis is determined by the scanner module of the robot 300. The second comparison target axis may be determined with reference to the wall corner area. For example, the wall corner area specified by the camera module and the wall corner area specified by the scanner module may be the same wall corner area or may be different wall corner areas having a predetermined positional relationship or a preset relationship.

Then, according to an embodiment of the present invention, the reference coordinate system associated with the camera module may be corrected with reference to the relationship between the first and second comparison axes above.

Additionally, if the temperature rises during the operation of the robot 300, an error may occur in the camera module. In this case, the reference coordinate system associated with the camera module can be corrected by referring to the angle between the floor surface where the robot 300 is located and the reference plane specified by the camera module.

For example, a candidate reference surface is specified using at least three points on the ground surface specified by a camera module, the number of points that exist within a predetermined distance from the candidate reference surface among a plurality of points on the ground surface is determined, and the candidate reference surface above is determined. Among the plurality of candidate reference surfaces including, the candidate reference surface with the number of the above points above a predetermined level may be determined as the reference surface specified by the camera module.

Meanwhile, according to an embodiment of the present invention, when the error rate (specifically, the error rate related to the angle difference between the ground surface and the roll direction of the camera module) is above a predetermined level with reference to the temperature of the camera module of the robot 300, the above Corrections may be made.

Additionally, according to one embodiment of the present invention, during the process of operating the robot 300, the wheels of the robot 300 may be worn or the floor of the restaurant may be uneven. In this case, movement attribute information of the robot 300 may be corrected with reference to at least one of the movement distance and rotation angle of the robot 300 determined based on a predetermined point specified by the scanner module. Meanwhile, according to one embodiment of the present invention, the process of correcting the movement attribute information of the robot 300 may be performed simultaneously with the process of correcting the reference coordinate system associated with the camera module, and may be performed before or after depending on the ground condition, wear condition, etc. Or it may happen later.

Composition of the robot

The robot 300 according to an embodiment of the present invention performs tasks similar to those performed by at least one of a guide robot, a serving robot, a transport robot, a cleaning robot, a medical robot, an entertainment robot, a pet robot, and an unmanned flying robot. It may be a robot, and for this purpose, it may be implemented in various shapes to suit each task.

8 and 9 are diagrams illustrating the structure of a robot according to an embodiment of the present invention.

Referring to FIG. 8, the robot 300 may include a main body 810, driving units 820a, 820b, 820c, and 820d, and a processor 830.

For example, the main body 810 according to an embodiment of the present invention may include at least one loading space for loading an object to be transported or an object to be recovered. The object to be transported and the object to be recovered according to an embodiment of the present invention are concepts that collectively refer to all tangible objects that can be moved, and may include, for example, objects, animals, people, etc. For example, the object to be transported may be food, and the object to be recovered may be a container containing the food.

Referring to FIG. 9, for example, when the robot 300 is a serving robot, it may include a first space 910 and a second space 920 for providing objects to be transported and collecting objects to be recovered. there is. Additionally, the robot 300 may further include a third space 930, which is an expansion space provided through a detachable pillar, and can be provided with more loading space by adding more expansion spaces as needed. Additionally, the robot 300 may further include a tray 940 dedicated to objects to be transported or objects to be recovered. For example, the tray 940 may have a configuration in which a plurality of circular grooves are formed on its upper surface when viewed from above. Each circular groove may be formed so that the lower part of the cup containing the beverage is seated and easily fixed to some extent. The size of these circular grooves may vary. Additionally, a fourth space 950 that can be taken out through the side of the robot 300 may be further included below the first space 910 of the robot 300. The fourth space 950 according to an embodiment of the present invention may have a shape similar to a basket in which an empty space is formed inside the fourth space, the sides are closed, the upper surface is open, and the lower surface is closed. However, the loading space of the robot 300 according to the present invention is not limited to the contents listed above, and can be implemented in various ways, such as other types of loading space, within the scope of achieving the purpose of the present invention. You can.

Meanwhile, referring again to FIG. 8, the main body 810 is equipped with a camera module (e.g., a three-dimensional A camera) (not shown) and a scanner module (e.g., lidar sensor, etc.) (not shown) may be further included.

Next, the driving units 820a, 820b, 820c, and 820d according to an embodiment of the present invention are modules for moving the main body 810 to another point or modules for loading and unloading objects to be transported and objects to be recovered. It may be configured to include.

For example, the driving units 820a, 820b, 820c, and 820d are modules for moving the main body 810 to another point and may include modules for wheels, propellers, etc. that are driven electrically, mechanically, or hydraulically. , a module for loading and unloading the transport object and the retrieved object, and may include a robot arm module for mounting and transporting the transport object and the retrieved object.

Next, the processor 830 according to an embodiment of the present invention is electrically connected to the driving units 820a, 820b, 820c, and 820d and can perform a function of controlling the driving units 820a, 820b, 820c, and 820d. Data processing built into hardware (which may further include communication modules for communication with external systems), for example, having physically structured circuits to perform functions expressed as codes or instructions included within a program. It can mean a device. For example, data processing devices built into hardware like this include a microprocessor, central processing unit, processor core, multiprocessor, and application-specific integrated circuit (ASIC). , and may include processing devices such as FPGA (field programmable gate array).

In addition, the processor 830 may perform at least one function of the comparison target axis determination unit 210 and the correction unit 220 of the correction system 200 according to the present invention (for example, the corresponding function may be modularized). may be included in the processor 830), the comparison target axis determination unit 210, and the correction unit 220 through communication with an external system (not shown) that performs the function of at least one of the drive units 820a and 820b. , 820c, 820d) may also perform a function of controlling.

Specifically, the processor 830 determines the first comparison target axis with reference to the first target area specified by the camera module of the robot 300, and the first target area and the first target area specified by the scanner module of the robot 300. A function to determine the second comparison target axis with reference to the associated second target area and to correct the reference coordinate system associated with the camera module of the robot 300 by referring to the relationship between the first comparison target axis and the second comparison target axis. can be performed.

The embodiments according to the present invention described above can be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and usable by those skilled in the computer software field. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. medium), and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. A hardware device can be converted into one or more software modules to perform processing according to the invention and vice versa.

In the above, the present invention has been described in terms of specific details, such as specific components, and limited embodiments and drawings, but this is only provided to facilitate a more general understanding of the present invention, and the present invention is not limited to the above embodiments. Anyone with ordinary knowledge in the technical field to which the invention pertains can make various modifications and changes from this description.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the patent claims described below as well as all scopes equivalent to or equivalently changed from the scope of the claims are within the scope of the spirit of the present invention. It will be said to belong to

100: communication network
200: correction system
210: Axis determination unit to be compared
220: Correction unit
230: Department of Communications
240: control unit
300: robot

Claims (23)

As a method for controlling a robot,
A first comparison target axis is determined with reference to a first target area specified by the robot's camera module, and a second comparison is made with reference to a second target area specified by the robot's scanner module and associated with the first target area. determining the target axis, and
Comprising the step of correcting a reference coordinate system associated with the camera module with reference to the relationship between the first comparison target axis and the second comparison target axis.
method. According to paragraph 1,
The first target area or the second target area includes a point or object where two or more edges meet at the location where the robot is located.
method. According to paragraph 1,
In the determination step, the first comparison target axis is determined with reference to the edge specified in the first target area, and the second comparison target axis is determined with reference to the edge specified in the second target area.
method. According to paragraph 1,
In the correction step, the reference coordinate system associated with the camera module is corrected by referring to the relationship between the floor surface on which the robot is located and the reference surface specified by the camera module.
method. According to paragraph 4,
Correcting the reference coordinate system associated with the camera module by referring to the angle between the floor surface on which the robot is located and the reference surface specified by the camera module.
method. According to paragraph 4,
Specifies a candidate reference surface using at least three points on the ground surface specified by the camera module, determines the number of points that exist within a predetermined distance from the candidate reference surface among a plurality of points on the ground surface, and includes the candidate reference surface. Among a plurality of candidate reference surfaces, the candidate reference surface with the number of points above a predetermined level is determined as the reference surface specified by the camera module.
method. According to clause 4,
A candidate reference surface is specified using at least three points on the ground surface specified by the camera module, a point that exists within a predetermined distance from the candidate reference surface among the plurality of points on the ground surface is determined, and a plurality of points including the candidate reference surface are determined. Determining the reference plane specified by the camera module by referring to the point among the candidate reference planes of
method. In clause 7,
Determining a reference surface specified by the camera module by referring to the result of regression analysis of the point among the plurality of candidate reference surfaces.
method. According to paragraph 1,
In the correction step, correcting the reference coordinate system associated with the camera module with reference to the angle between the first comparison target axis and the second comparison target axis.
method. According to paragraph 1,
The correction step includes correcting the movement attribute information of the robot with reference to at least one of the movement distance and rotation angle of the robot determined based on a predetermined point specified by the scanner module.
method. According to clause 10,
The movement attribute information includes information about at least one of the size of the wheels and the length of the wheel base of the robot.
method. A non-transitory computer-readable recording medium recording a computer program for executing the method according to claim 1. As a system for controlling a robot,
A first comparison target axis is determined with reference to a first target area specified by the robot's camera module, and a second comparison is made with reference to a second target area specified by the robot's scanner module and associated with the first target area. A comparison target axis determination unit that determines the target axis, and
Comprising a correction unit that corrects a reference coordinate system associated with the camera module with reference to the relationship between the first comparison target axis and the second comparison target axis.
system. According to clause 13,
The first target area or the second target area includes a point or object where two or more edges meet at the location where the robot is located.
system. According to clause 13,
The comparison target axis determination unit determines the first comparison target axis with reference to an edge specified in the first target area, and determines the second comparison target axis with reference to the edge specified in the second target area.
system. According to clause 13,
The correction unit corrects the reference coordinate system associated with the camera module with reference to the relationship between the floor surface on which the robot is located and the reference surface specified by the camera module.
system. According to clause 16,
The correction unit corrects the reference coordinate system associated with the camera module with reference to the angle between the floor surface on which the robot is located and the reference surface specified by the camera module.
system. According to clause 16,
The correction unit specifies a candidate reference surface using at least three points on the ground surface specified by the camera module, and determines the number of points that exist within a predetermined distance from the candidate reference surface among a plurality of points on the ground surface, Among a plurality of candidate reference surfaces including candidate reference surfaces, a candidate reference surface with the number of points above a predetermined level is determined as the reference surface specified by the camera module.
system. According to clause 16,
The correction unit specifies a candidate reference surface using at least three points on the ground surface specified by the camera module, determines a point that exists within a predetermined distance from the candidate reference surface among a plurality of points on the ground surface, and determines the candidate reference surface. Determining a reference surface specified by the camera module with reference to the point among a plurality of candidate reference surfaces including
system. According to clause 19,
Determining a reference surface specified by the camera module by referring to the result of regression analysis of the point among the plurality of candidate reference surfaces.
system. According to clause 13,
The correction unit corrects the reference coordinate system associated with the camera module with reference to the angle between the first comparison target axis and the second comparison target axis.
system. According to clause 13,
The correction unit corrects the movement attribute information of the robot with reference to at least one of the movement distance and rotation angle of the robot determined based on a predetermined point specified by the scanner module.
system. According to clause 22,
The movement attribute information includes information about at least one of the size of the wheels and the length of the wheel base of the robot.
system.

Images